Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 6767
    Prev
    Next
    INDEX
    Explanations

    mentions of actions or characteristics related to someone

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "someone."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ories
    -0.86
    osterone
    -0.81
    èª
    -0.70
    eed
    -0.68
    ory
    -0.68
    inders
    -0.67
    heny
    -0.67
    DOS
    -0.66
    AIN
    -0.66
    irth
    -0.65
    POSITIVE LOGITS
     else
    1.73
    Else
    1.26
     Else
    1.06
    else
    1.04
    WithNo
    0.88
     who
    0.81
     smugg
    0.72
     knowledgeable
    0.72
     unlucky
    0.69
     identifiable
    0.68
    Activations Density 0.039%

    No Known Activations